Support saving and loading of SingleCellExperiment objects with the…

… new takane specification (#1)

* Add readers and writer for SCE
* Add tests
* Update github action to run tests from Python 3.8 to 3.12
* Update docstrings

.github/workflows/pypi-publish.yml

@@ -1,3 +1,6 @@
+# This workflow will install Python dependencies, run tests and lint with a single version of Python
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
 name: Publish to PyPI
 
 on:
@@ -6,32 +9,43 @@ on:
 
 jobs:
   build:
+
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v3
-
+    - uses: actions/checkout@v2
     - name: Set up Python 3.9
       uses: actions/setup-python@v2
       with:
         python-version: 3.9
-        cache: 'pip'
-
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install pytest tox
-
+        pip install flake8 pytest tox
+    # - name: Lint with flake8
+    #   run: |
+    #     # stop the build if there are Python syntax errors or undefined names
+    #     flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+    #     # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+    #     # flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
     - name: Test with tox
       run: |
         tox
-
-    - name: Build package
+    - name: Build docs
+      run: |
+        tox -e docs
+    - run: touch ./docs/_build/html/.nojekyll
+    - name: GH Pages Deployment
+      uses: JamesIves/[email protected]
+      with:
+        branch: gh-pages # The branch the action should deploy to.
+        folder: ./docs/_build/html
+        clean: true # Automatically remove deleted files from the deploy branch
+    - name: Build Project and Publish
       run: |
         python -m tox -e clean,build
-
     - name: Publish package
       uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
       with:
         user: __token__
-        password: ${{ secrets.PYPI_PASSWORD }}
+        password: ${{ secrets.PYPI_PASSWORD }}

.github/workflows/pypi-test.yml

@@ -2,29 +2,36 @@ name: Test the library
 
 on:
   push:
-    branches:
-      - master
+    branches: [ master ]
   pull_request:
+    branches: [ master ]
 
 jobs:
   build:
+
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [ '3.8', '3.9', '3.10', '3.11', '3.12' ]
 
+    name: Python ${{ matrix.python-version }}
     steps:
-      - name: Check out repo
-        uses: actions/checkout@v3
-
-      - name: Set up Python 3.9
-        uses: actions/setup-python@v2
-        with:
-          python-version: 3.9
-          cache: 'pip'
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          python -m pip install tox
-  
-      - name: Test with tox
-        run: |
-          tox
+    - uses: actions/checkout@v2
+    - name: Setup Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+        cache: 'pip'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install flake8 pytest tox
+    # - name: Lint with flake8
+    #   run: |
+    #     # stop the build if there are Python syntax errors or undefined names
+    #     flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+    #     # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+    #     # flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with tox
+      run: |
+        tox

setup.cfg

@@ -5,17 +5,17 @@
 
 [metadata]
 name = dolomite-sce
-description = Add a short description here!
+description = Save and load single-cell experiments in the dolomite framework!
 author = LTLA
 author_email = [email protected]
 license = MIT
 license_files = LICENSE.txt
 long_description = file: README.md
 long_description_content_type = text/markdown; charset=UTF-8; variant=GFM
-url = https://github.com/pyscaffold/pyscaffold/
+url = https://github.com/ArtifactDB/dolomite-sce
 # Add here related links, for example:
 project_urls =
-    Documentation = https://pyscaffold.org/
+    Documentation = https://github.com/ArtifactDB/dolomite-sce
 #    Source = https://github.com/pyscaffold/pyscaffold/
 #    Changelog = https://pyscaffold.org/en/latest/changelog.html
 #    Tracker = https://github.com/pyscaffold/pyscaffold/issues
@@ -41,17 +41,17 @@ package_dir =
     =src
 
 # Require a min/specific Python version (comma-separated conditions)
-# python_requires = >=3.8
+python_requires = >=3.8
 
 # Add here dependencies of your project (line-separated), e.g. requests>=2.2,<3.0.
 # Version specifiers like >=2.2,<3.0 avoid problems due to API changes in
 # new major versions. This works if the required packages follow Semantic Versioning.
 # For more information, check out https://semver.org/.
 install_requires =
     importlib-metadata; python_version<"3.8"
-    dolomite_base
-    dolomite_se
-    SummarizedExperiment
+    dolomite_base==0.2.0-alpha6
+    dolomite_se==0.1.0-alpha2
+    SingleCellExperiment>=0.4.3,<0.5.0
 
 
 [options.packages.find]

src/dolomite_sce/__init__.py

@@ -16,4 +16,5 @@
     del version, PackageNotFoundError
 
 
-from .load_single_cell_experiment import load_single_cell_experiment
+from .read_single_cell_experiment import read_single_cell_experiment
+from .save_single_cell_experiment import save_single_cell_experiment

src/dolomite_sce/read_single_cell_experiment.py

@@ -0,0 +1,103 @@
+import json
+import os
+
+import dolomite_base as dl
+from dolomite_base.read_object import read_object_registry
+from dolomite_se import read_common_se_props
+from singlecellexperiment import SingleCellExperiment
+
+read_object_registry[
+    "single_cell_experiment"
+] = "dolomite_sce.read_single_cell_experiment"
+
+
+def read_single_cell_experiment(
+    path: str, metadata: dict, **kwargs
+) -> SingleCellExperiment:
+    """Load a
+    :py:class:`~singlecellexperiment.SingleCellExperiment.SingleCellExperiment`
+    from its on-disk representation.
+
+    This method should generally not be called directly but instead be invoked by
+    :py:meth:`~dolomite_base.read_object.read_object`.
+
+    Args:
+        path:
+            Path to the directory containing the object.
+
+        metadata:
+            Metadata for the object.
+
+        kwargs:
+            Further arguments, ignored.
+
+    Returns:
+        A
+        :py:class:`~singlecellexperiment.SingleCellExperiment.SingleCellExperiment`
+        with file-backed arrays in the assays.
+    """
+
+    _row_data, _column_data, _assays = read_common_se_props(path)
+
+    _main_expt_name = None
+    if "main_experiment_name" in metadata["single_cell_experiment"]:
+        _main_expt_name = metadata["single_cell_experiment"]["main_experiment_name"]
+
+    sce = SingleCellExperiment(
+        assays=_assays,
+        row_data=_row_data,
+        column_data=_column_data,
+        main_experiment_name=_main_expt_name,
+    )
+
+    _meta_path = os.path.join(path, "other_data")
+    if os.path.exists(_meta_path):
+        _meta = dl.read_object(_meta_path)
+        sce = sce.set_metadata(_meta.as_dict())
+
+    _ranges_path = os.path.join(path, "row_ranges")
+    if os.path.exists(_ranges_path):
+        _ranges = dl.read_object(_ranges_path)
+        sce = sce.set_row_ranges(_ranges)
+
+    _rdim_path = os.path.join(path, "reduced_dimensions")
+    if os.path.exists(_rdim_path):
+        _rdims = {}
+
+        with open(os.path.join(_rdim_path, "names.json"), "r") as handle:
+            _rdim_names = json.load(handle)
+
+        for _aidx, _aname in enumerate(_rdim_names):
+            _rdim_read_path = os.path.join(_rdim_path, str(_aidx))
+
+            try:
+                _rdims[_aname] = dl.read_object(_rdim_read_path)
+            except Exception as ex:
+                raise RuntimeError(
+                    f"failed to load reduced dimension '{_aname}' from '{path}'; "
+                    + str(ex)
+                )
+
+        sce = sce.set_reduced_dims(_rdims)
+
+    _alt_path = os.path.join(path, "alternative_experiments")
+    if os.path.exists(_alt_path):
+        _alts = {}
+
+        with open(os.path.join(_alt_path, "names.json"), "r") as handle:
+            _alt_names = json.load(handle)
+
+        for _aidx, _aname in enumerate(_alt_names):
+            _alt_read_path = os.path.join(_alt_path, str(_aidx))
+
+            try:
+                _alts[_aname] = dl.read_object(_alt_read_path)
+            except Exception as ex:
+                raise RuntimeError(
+                    f"failed to load alternative experiment '{_aname}' from '{path}'; "
+                    + str(ex)
+                )
+
+        sce = sce.set_alternative_experiments(_alts)
+
+    return sce